[SPARK-5769] Set params in constructors and in setParams in Python ML pipelines

This PR allow Python users to set params in constructors and in setParams, where we use decorator `keyword_only` to force keyword arguments. The trade-off is discussed in the design doc of SPARK-4586.

Generated doc:
![screen shot 2015-02-12 at 3 06 58 am](https://cloud.githubusercontent.com/assets/829644/6166491/9cfcd06a-b265-11e4-99ea-473d866634fc.png)

CC: davies rxin

Author: Xiangrui Meng <meng@databricks.com>

Closes #4564 from mengxr/py-pipeline-kw and squashes the following commits:

fedf720 [Xiangrui Meng] use toDF
d565f2c [Xiangrui Meng] Merge remote-tracking branch 'apache/master' into py-pipeline-kw
cbc15d3 [Xiangrui Meng] fix style
5032097 [Xiangrui Meng] update pipeline signature
950774e [Xiangrui Meng] simplify keyword_only and update constructor/setParams signatures
fdde5fc [Xiangrui Meng] fix style
c9384b8 [Xiangrui Meng] fix sphinx doc
8e59180 [Xiangrui Meng] add setParams and make constructors take params, where we force keyword args

1 files changed, 15 insertions, 0 deletions

diff --git a/python/pyspark/ml/util.py b/python/pyspark/ml/util.py
index b1caa84b63..81d3f0882b 100644
--- a/python/pyspark/ml/util.py
+++ b/python/pyspark/ml/util.py
@@ -15,6 +15,7 @@
 # limitations under the License.
 #
 
+from functools import wraps
 import uuid
 
 
@@ -32,6 +33,20 @@ def inherit_doc(cls):
     return cls
 
 
+def keyword_only(func):
+    """
+    A decorator that forces keyword arguments in the wrapped method
+    and saves actual input keyword arguments in `_input_kwargs`.
+    """
+    @wraps(func)
+    def wrapper(*args, **kwargs):
+        if len(args) > 1:
+            raise TypeError("Method %s forces keyword arguments." % func.__name__)
+        wrapper._input_kwargs = kwargs
+        return func(*args, **kwargs)
+    return wrapper
+
+
 class Identifiable(object):
     """
     Object with a unique ID.